© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1173
    Prev
    Next
    INDEX
    Explanations

    while loops and end conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dle
    -0.08
    epen
    -0.08
    ĮĢ
    -0.08
    hti
    -0.08
    mojom
    -0.08
    ISED
    -0.08
    .localized
    -0.08
    ostro
    -0.08
    tima
    -0.08
    _san
    -0.07
    POSITIVE LOGITS
    ermann
    0.07
    inson
    0.07
    æ´½
    0.07
    æħķ
    0.07
     reading
    0.06
    éŀłèº¬
    0.06
    isons
    0.06
    สà¸Ļิà¸Ĺ
    0.06
    dat
    0.06
    éĴ¦
    0.06
    Activations Density 0.007%

    No Known Activations